Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4859 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.2245. Min Act: -0.1700
Data Index: 4104135 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.1308. Min Act: -0.1700
Data Index: 4753773 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.1308. Min Act: -0.1700
Data Index: 5174720 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.1308. Min Act: -0.1700
Data Index: 6325111 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.1620. Min Act: -0.1700
Data Index: 5431222 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0995. Min Act: -0.1700
Data Index: 417158 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0995. Min Act: -0.1700
Data Index: 5705129 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0995. Min Act: -0.1700
Data Index: 4939643 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0995. Min Act: -0.1700
Data Index: 3992711 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0995. Min Act: -0.1700
Data Index: 6136540 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0683. Min Act: -0.1700
Data Index: 3221802 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0683. Min Act: -0.1700
Data Index: 543402 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 407486 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 1314725 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 922030 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 8398834 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0058. Min Act: -0.1700
Data Index: 721246 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 5120909 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0370. Min Act: -0.1700
Data Index: 4048389 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2245. Min Range: -5.2245
Max Act: 5.0058. Min Act: -0.1700
Data Index: 3883648 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19